Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh

Time-series analyses of temperature data are important for investigating temperature variation and predicting temperature change. Here, Mann–Kendall (M–K) analyses of temperature time-series data in northeastern Bangladesh indicated increasing trends (Sen’s slope of maximum and minimum yearly temper...

Full description

Bibliographic Details
Main Authors: Ahmad Hasan Nury, Khairul Hasan, Md. Jahir Bin Alam
Format: Article
Language:English
Published: Elsevier 2017-01-01
Series:Journal of King Saud University: Science
Subjects:
ANN
Online Access:http://www.sciencedirect.com/science/article/pii/S1018364715001135
id doaj-5f197e99ef6a45d19537470cf1b91b8c
record_format Article
spelling doaj-5f197e99ef6a45d19537470cf1b91b8c2020-11-24T21:23:44ZengElsevierJournal of King Saud University: Science1018-36472017-01-01291476110.1016/j.jksus.2015.12.002Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern BangladeshAhmad Hasan NuryKhairul HasanMd. Jahir Bin AlamTime-series analyses of temperature data are important for investigating temperature variation and predicting temperature change. Here, Mann–Kendall (M–K) analyses of temperature time-series data in northeastern Bangladesh indicated increasing trends (Sen’s slope of maximum and minimum yearly temperature at Sylhet of 0.03 °C and 0.026 °C, respectively, and a minimum temperature at Sreemangal of 0.024 °C) except for the maximum temperature at Sreemangal. The linear trends showed that the maximum temperature is increasing by 2.97 °C and 0.59 °C per hundred years, and the minimum, by 2.17 °C and 2.73 °C per hundred years at the Sylhet and Sreemangal stations, indicating that climate change is affecting temperature in this area. This paper presents an alternative method for temperature prediction by combining the wavelet technique with an autoregressive integrated moving average (ARIMA) model and an artificial neural network (ANN) applied to monthly maximum and minimum temperature data. The data are divided into a training dataset (1957–2000) to construct the models and a testing dataset (2001–2012) to estimate their performance. The calibration and validation performance of the models is evaluated statistically, and the relative performance based on the predictive capability of out-of-sample forecasts is assessed. The results indicate that the wavelet-ARIMA model is more effective than the wavelet-ANN model.http://www.sciencedirect.com/science/article/pii/S1018364715001135Mann–Kendall testARIMAANNWavelet-ARIMAWavelet-ANN
collection DOAJ
language English
format Article
sources DOAJ
author Ahmad Hasan Nury
Khairul Hasan
Md. Jahir Bin Alam
spellingShingle Ahmad Hasan Nury
Khairul Hasan
Md. Jahir Bin Alam
Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh
Journal of King Saud University: Science
Mann–Kendall test
ARIMA
ANN
Wavelet-ARIMA
Wavelet-ANN
author_facet Ahmad Hasan Nury
Khairul Hasan
Md. Jahir Bin Alam
author_sort Ahmad Hasan Nury
title Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh
title_short Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh
title_full Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh
title_fullStr Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh
title_full_unstemmed Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh
title_sort comparative study of wavelet-arima and wavelet-ann models for temperature time series data in northeastern bangladesh
publisher Elsevier
series Journal of King Saud University: Science
issn 1018-3647
publishDate 2017-01-01
description Time-series analyses of temperature data are important for investigating temperature variation and predicting temperature change. Here, Mann–Kendall (M–K) analyses of temperature time-series data in northeastern Bangladesh indicated increasing trends (Sen’s slope of maximum and minimum yearly temperature at Sylhet of 0.03 °C and 0.026 °C, respectively, and a minimum temperature at Sreemangal of 0.024 °C) except for the maximum temperature at Sreemangal. The linear trends showed that the maximum temperature is increasing by 2.97 °C and 0.59 °C per hundred years, and the minimum, by 2.17 °C and 2.73 °C per hundred years at the Sylhet and Sreemangal stations, indicating that climate change is affecting temperature in this area. This paper presents an alternative method for temperature prediction by combining the wavelet technique with an autoregressive integrated moving average (ARIMA) model and an artificial neural network (ANN) applied to monthly maximum and minimum temperature data. The data are divided into a training dataset (1957–2000) to construct the models and a testing dataset (2001–2012) to estimate their performance. The calibration and validation performance of the models is evaluated statistically, and the relative performance based on the predictive capability of out-of-sample forecasts is assessed. The results indicate that the wavelet-ARIMA model is more effective than the wavelet-ANN model.
topic Mann–Kendall test
ARIMA
ANN
Wavelet-ARIMA
Wavelet-ANN
url http://www.sciencedirect.com/science/article/pii/S1018364715001135
work_keys_str_mv AT ahmadhasannury comparativestudyofwaveletarimaandwaveletannmodelsfortemperaturetimeseriesdatainnortheasternbangladesh
AT khairulhasan comparativestudyofwaveletarimaandwaveletannmodelsfortemperaturetimeseriesdatainnortheasternbangladesh
AT mdjahirbinalam comparativestudyofwaveletarimaandwaveletannmodelsfortemperaturetimeseriesdatainnortheasternbangladesh
_version_ 1725991386842398720